Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/easyship/easyship-mcp-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/easyship/easyship-mcp-plugin/easyship-safety)<a href="https://agentmods.dev/rules/easyship/easyship-mcp-plugin/easyship-safety"><img src="https://agentmods.dev/badge/rules/easyship/easyship-mcp-plugin/easyship-safety.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00347 | $0.00347 |
| Opus 5 | $0.00173 | $0.00173 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
easyship-safety scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Easyship Safety Rules
Destructive actions require confirmation
Before calling delete_shipment, cancel_shipment, or cancel_pickup, always ask the user to confirm. Show the shipment/pickup ID and current status so they can make an informed decision.
Never expose API tokens
Never display, log, or include EASYSHIP_API_ACCESS_TOKEN in responses, code snippets, or file contents. If the user shares a token in chat, warn them and suggest rotating it.
Validate required fields before API calls
Before calling create_shipment, verify that all required address fields are present: contact name, email, phone, street, city, and country code for both origin and destination. If any are missing, ask the user rather than guessing.
Before calling get_rates, ensure origin country, destination country, weight, and all three dimensions (length, width, height) are provided. Prompt for missing values.
Handle errors gracefully
If an API call returns an error, present the error message clearly and suggest a fix. Common issues:
- 401 Unauthorized → token is missing or expired, direct to https://app.easyship.com/connect/api
- 422 Unprocessable → missing or invalid fields, show which fields need correction
- 429 Rate limited → wait and retry, inform the user
Currency and units
Always include the currency code when displaying prices. Do not convert currencies unless the user asks. Weights are in kg and dimensions in cm unless the user specifies otherwise.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 33 lines · 347 tokens per session scan A 3a7c4a7fdade
easyship-safety is a cursor rule published in the GitHub repository easyship/easyship-mcp-plugin (0 stars, last pushed 2mo ago), licensed MIT. It adds 347 tokens to every session, about $0.0017 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
paddle-integration
Conventions for Paddle integration code.
vtex-io-vtex-io-storefront-theme-app
Apply when designing or modifying a VTEX IO storefront theme app — the app that owns store/blocks.json, store/routes.json, store/templates/, store/contentSchemas.json, and the storefront page tree assembled from store.home, store.product, store.search, store.custom, and other native page templates. Covers how a theme…
faststore-faststore-storefront-ref-project-structure-routes-and-config
FastStore project structure, routes, CLI build pipeline, store configuration (discovery.config.js), and naming conventions. Use when understanding how a FastStore project is organized, how the @faststore/cli works, what files to create or modify, how routing works, or how to configure store settings like SEO, API…
faststore-faststore-storefront-ref-graphql-types-queries-and-mutations
Complete FastStore GraphQL BFF API reference including all built-in root queries, root mutations, and type definitions. Use when querying product, collection, search, cart, session, shipping, or user order data, when extending existing types with new fields, or when looking up available fields on types like…
medusa
Medusa rules and best practices. These rules should be used when building applications with Medusa.